
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import scipy

print("✅ All libraries loaded.")
print("NumPy:", np.__version__)
print("Pandas:", pd.__version__)
print("Seaborn:", sns.__version__)
print("SciPy:", scipy.__version__)

✅ All libraries loaded.
NumPy: 1.26.4
Pandas: 2.3.0+4.g1dfc98e16a
Seaborn: 0.11.2
SciPy: 1.13.1


df = pd.read_csv('water_potability.csv')
df.head(50)


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3276 entries, 0 to 3275
Data columns (total 10 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   ph               2785 non-null   float64
 1   Hardness         3276 non-null   float64
 2   Solids           3276 non-null   float64
 3   Chloramines      3276 non-null   float64
 4   Sulfate          2495 non-null   float64
 5   Conductivity     3276 non-null   float64
 6   Organic_carbon   3276 non-null   float64
 7   Trihalomethanes  3114 non-null   float64
 8   Turbidity        3276 non-null   float64
 9   Potability       3276 non-null   int64  
dtypes: float64(9), int64(1)
memory usage: 256.1 KB


df[df['Potability'] == 1]


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3276 entries, 0 to 3275
Data columns (total 10 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   ph               2785 non-null   float64
 1   Hardness         3276 non-null   float64
 2   Solids           3276 non-null   float64
 3   Chloramines      3276 non-null   float64
 4   Sulfate          2495 non-null   float64
 5   Conductivity     3276 non-null   float64
 6   Organic_carbon   3276 non-null   float64
 7   Trihalomethanes  3114 non-null   float64
 8   Turbidity        3276 non-null   float64
 9   Potability       3276 non-null   int64  
dtypes: float64(9), int64(1)
memory usage: 256.1 KB


# check for duplicated rows 
df.duplicated().sum()

0


df.describe()


df.isna().sum()

ph                 491
Hardness             0
Solids               0
Chloramines          0
Sulfate            781
Conductivity         0
Organic_carbon       0
Trihalomethanes    162
Turbidity            0
Potability           0
dtype: int64


df.dtypes

ph                 float64
Hardness           float64
Solids             float64
Chloramines        float64
Sulfate            float64
Conductivity       float64
Organic_carbon     float64
Trihalomethanes    float64
Turbidity          float64
Potability           int64
dtype: object


df['ph'].fillna(df['ph'].median(), inplace=True)
df['Sulfate'].fillna(df['Sulfate'].median(), inplace=True)
df['Trihalomethanes'].fillna(df['Trihalomethanes'].mean(), inplace=True)

C:\Users\asus\AppData\Local\Temp\ipykernel_16508\1952783639.py:1: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.
The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.

For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.


  df['ph'].fillna(df['ph'].median(), inplace=True)
C:\Users\asus\AppData\Local\Temp\ipykernel_16508\1952783639.py:2: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.
The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.

For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.


  df['Sulfate'].fillna(df['Sulfate'].median(), inplace=True)
C:\Users\asus\AppData\Local\Temp\ipykernel_16508\1952783639.py:3: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.
The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.

For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.


  df['Trihalomethanes'].fillna(df['Trihalomethanes'].mean(), inplace=True)


df.isna().sum()

ph                 0
Hardness           0
Solids             0
Chloramines        0
Sulfate            0
Conductivity       0
Organic_carbon     0
Trihalomethanes    0
Turbidity          0
Potability         0
dtype: int64


df[df['Potability'] == 1]


# Example: pH should not be 0 in real water
df[df['ph'] == 0]


df.loc[df['ph'] == 0, 'ph'] = np.nan
df['ph'].fillna(df['ph'].median(), inplace=True)

C:\Users\asus\AppData\Local\Temp\ipykernel_16508\1201209032.py:2: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.
The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.

For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.


  df['ph'].fillna(df['ph'].median(), inplace=True)


df[df['ph'] == 0]


df.describe()


# Total number of rows
total_samples = len(df)

# Number of safe water samples (Potability = 1)
safe_samples = df[df['Potability'] == 1].shape[0]

# Calculate percentage
safe_percentage = (safe_samples / total_samples) * 100

print(f"Safe water samples: {safe_samples} out of {total_samples} ({safe_percentage:.2f}%)")

Safe water samples: 1278 out of 3276 (39.01%)


# Step 1: Remove old Potability column
df.drop(columns=['Potability'], inplace=True)

# Step 2: Scoring Function (based on WHO recommended ranges)
def calculate_potability_score(row):
    score = 0
    
    if 6.5 <= row['ph'] <= 8.5: score += 15
    if row['Solids'] < 500: score += 10
    if row['Chloramines'] < 4: score += 10
    if row['Sulfate'] < 250: score += 10
    if row['Trihalomethanes'] < 80: score += 10
    if row['Organic_carbon'] < 5: score += 10
    if row['Conductivity'] < 1500: score += 10
    if row['Turbidity'] < 5: score += 10
    if row['Hardness'] < 120: score += 5
    
    return score

# Step 3: Apply score to each row
df['Potability_Score'] = df.apply(calculate_potability_score, axis=1)

# Step 4: Map score into categories
def map_potability_level(score):
    if score < 41:
        return 'Very Poor'
    elif score < 61:
        return 'Poor'
    elif score < 76:
        return 'Average'
    elif score < 91:
        return 'Good'
    else:
        return 'Very Good'

df['Potability_Level'] = df['Potability_Score'].apply(map_potability_level)

# Step 5: Ensure correct data types
df['Potability_Score'] = df['Potability_Score'].astype(int)
df['Potability_Level'] = df['Potability_Level'].astype('category')


import seaborn as sns
import matplotlib.pyplot as plt

plt.figure(figsize=(8,5))
sns.countplot(x='Potability_Level', data=df, palette='Spectral', order=df['Potability_Level'].value_counts().index)
plt.title("Distribution of Water Quality Levels")
plt.xlabel("Potability Level")
plt.ylabel("Number of Samples")
plt.grid(True, axis='y')
plt.tight_layout()
plt.show()

C:\ProgramData\Anaconda3\lib\site-packages\seaborn\categorical.py:253: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.
  grouped_vals = vals.groupby(grouper)


import pandas as pd
import plotly.express as px
from sklearn.preprocessing import MinMaxScaler

# Step 1: Only keep very poor water samples
very_poor_df = df[df["Potability_Level"] == "Very Poor"]

# Step 2: Select only chemical columns
chemical_cols = ['ph', 'Hardness', 'Solids', 'Chloramines', 'Sulfate',
                 'Conductivity', 'Organic_carbon', 'Trihalomethanes', 'Turbidity']

# Step 3: Normalize all columns to 0–10 scale using MinMaxScaler
scaler = MinMaxScaler(feature_range=(0, 10))
normalized_data = scaler.fit_transform(very_poor_df[chemical_cols])

# Step 4: Take mean of each chemical (for Very Poor category)
mean_normalized = pd.DataFrame(normalized_data, columns=chemical_cols).mean().sort_values(ascending=False)

# Step 5: Create Plotly bar chart
fig = px.bar(
    x=mean_normalized.values,
    y=mean_normalized.index,
    orientation='h',
    labels={'x': 'Normalized Mean Value (0–10)', 'y': 'Chemical'},
    title='Normalized Chemical Levels in Very Poor Water Samples',
    text=mean_normalized.round(2)
)

fig.update_traces(marker_color='indianred', textposition='outside')
fig.update_layout(xaxis_range=[0, 10])

fig.show()


# 📦 1. Import Libraries
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split

# 📂 2. Load and Clean Dataset
df = pd.read_csv("water_potability.csv")
df.fillna(df.median(numeric_only=True), inplace=True)

# 📊 3. Define Custom Scoring Function (Safe Bonus + Danger Penalty)
def custom_score(row):
    score = 0

    # ✅ Bonus: Safe ranges = +10 each
    if 6.5 <= row['ph'] <= 8.5: score += 10
    if row['Hardness'] <= 300: score += 10
    if row['Solids'] <= 5000: score += 10
    if row['Chloramines'] <= 4: score += 10
    if row['Sulfate'] <= 250: score += 10
    if row['Conductivity'] <= 800: score += 10
    if row['Organic_carbon'] <= 10: score += 10
    if row['Trihalomethanes'] <= 80: score += 10
    if row['Turbidity'] <= 5: score += 10

    # ❌ Penalty: More dangerous = more negative score
    def penalty(value, limit, factor=1):
        return max(0, (value - limit) // (limit * factor) + 1) * 10

    if row['Trihalomethanes'] > 80:
        score -= penalty(row['Trihalomethanes'], 80, factor=0.5)
    if row['Turbidity'] > 5:
        score -= penalty(row['Turbidity'], 5, factor=0.2)
    if row['Chloramines'] > 4:
        score -= penalty(row['Chloramines'], 4, factor=0.5)
    if row['Sulfate'] > 250:
        score -= penalty(row['Sulfate'], 250, factor=0.5)
    if row['Conductivity'] > 800:
        score -= penalty(row['Conductivity'], 800, factor=0.5)
    if row['Solids'] > 5000:
        score -= penalty(row['Solids'], 5000, factor=1)
    if row['Organic_carbon'] > 10:
        score -= penalty(row['Organic_carbon'], 10, factor=0.5)

    if 6.5 <= row['ph'] <= 8.5:
        score += 10
    else:
        score -= 10

    if row['Hardness'] > 300:
        score -= 10

    return max(score, 0)

# 🧮 4. Apply Scoring
df['Potability_Score'] = df.apply(custom_score, axis=1)

# 📈 5. Categorize Potability Level
def categorize(score):
    if score >= 80:
        return "Very Good"
    elif score >= 60:
        return "Good"
    elif score >= 40:
        return "Average"
    elif score >= 20:
        return "Poor"
    else:
        return "Very Poor"

df['Potability_Level'] = df['Potability_Score'].apply(categorize)

# 📚 6. Split Dataset for Any Further Use (e.g., model validation if needed)
train_df, test_df = train_test_split(df, test_size=0.2, random_state=42)

# 🤖 7. Function to Predict from User Input
def predict_potability(user_input):
    row = pd.Series(user_input)
    score = custom_score(row)
    level = categorize(score)
    return score, level

# 🧪 8. Example Prediction
user_input = {
    'ph': 7.2,                 # 6.5 – 8.5
    'Hardness': 100,           # 60 – 120 mg/L (as CaCO₃)
    'Solids': 400,             # < 500 mg/L
    'Chloramines': 2.5,        # < 4.0 mg/L
    'Sulfate': 210,            # < 250 mg/L
    'Conductivity': 700,       # < 800 µS/cm
    'Organic_carbon': 4,       # < 5 mg/L
    'Trihalomethanes': 70,     # < 80 µg/L
    'Turbidity': 3.5           # < 5 NTU (preferably < 1 NTU)
}

score, level = predict_potability(user_input)
print(f"Predicted Score: {score} / 100")
print(f"Water Quality: {level}")

Predicted Score: 100 / 100
Water Quality: Very Good

	ph	Hardness	Solids	Chloramines	Sulfate	Conductivity	Organic_carbon	Trihalomethanes	Turbidity
0	NaN	204.890455	20791.318981	7.300212	368.516441	564.308654	10.379783	86.990970	2.963135
1	3.716080	129.422921	18630.057858	6.635246	NaN	592.885359	15.180013	56.329076	4.500656
2	8.099124	224.236259	19909.541732	9.275884	NaN	418.606213	16.868637	66.420093	3.055934
3	8.316766	214.373394	22018.417441	8.059332	356.886136	363.266516	18.436524	100.341674	4.628771
4	9.092223	181.101509	17978.986339	6.546600	310.135738	398.410813	11.558279	31.997993	4.075075
5	5.584087	188.313324	28748.687739	7.544869	326.678363	280.467916	8.399735	54.917862	2.559708
6	10.223862	248.071735	28749.716544	7.513408	393.663396	283.651634	13.789695	84.603556	2.672989
7	8.635849	203.361523	13672.091764	4.563009	303.309771	474.607645	12.363817	62.798309	4.401425
8	NaN	118.988579	14285.583854	7.804174	268.646941	389.375566	12.706049	53.928846	3.595017
9	11.180284	227.231469	25484.508491	9.077200	404.041635	563.885481	17.927806	71.976601	4.370562
10	7.360640	165.520797	32452.614409	7.550701	326.624353	425.383419	15.586810	78.740016	3.662292
11	7.974522	218.693300	18767.656682	8.110385	NaN	364.098230	14.525746	76.485911	4.011718
12	7.119824	156.704993	18730.813653	3.606036	282.344050	347.715027	15.929536	79.500778	3.445756
13	NaN	150.174923	27331.361962	6.838223	299.415781	379.761835	19.370807	76.509996	4.413974
14	7.496232	205.344982	28388.004887	5.072558	NaN	444.645352	13.228311	70.300213	4.777382
15	6.347272	186.732881	41065.234765	9.629596	364.487687	516.743282	11.539781	75.071617	4.376348
16	7.051786	211.049406	30980.600787	10.094796	NaN	315.141267	20.397022	56.651604	4.268429
17	9.181560	273.813807	24041.326280	6.904990	398.350517	477.974642	13.387341	71.457362	4.503661
18	8.975464	279.357167	19460.398131	6.204321	NaN	431.443990	12.888759	63.821237	2.436086
19	7.371050	214.496610	25630.320037	4.432669	335.754439	469.914551	12.509164	62.797277	2.560299
20	NaN	227.435048	22305.567414	10.333918	NaN	554.820086	16.331693	45.382815	4.133423
21	6.660212	168.283747	30944.363591	5.858769	310.930858	523.671298	17.884235	77.042318	3.749701
22	NaN	215.977859	17107.224226	5.607060	326.943978	436.256194	14.189062	59.855476	5.459251
23	3.902476	196.903247	21167.500099	6.996312	NaN	444.478883	16.609033	90.181676	4.528523
24	5.400302	140.739062	17266.593422	10.056852	328.358241	472.874073	11.256381	56.931906	4.824786
25	6.514415	198.767351	21218.702871	8.670937	323.596349	413.290450	14.900000	79.847843	5.200885
26	3.445062	207.926260	33424.768678	8.782147	384.007006	441.785876	13.805902	30.284597	4.184397
27	NaN	145.768181	13224.935639	7.906445	304.001993	298.990666	12.729525	49.536849	4.004871
28	NaN	266.421018	26362.965012	7.700063	395.389490	364.480107	10.348951	53.008381	3.991564
29	NaN	148.153061	15193.413474	9.046833	307.011793	563.804743	16.568656	52.676185	6.038185
30	7.181449	209.625601	15196.229987	5.994679	338.336431	342.111286	7.922598	71.537953	5.088860
31	9.825490	190.756618	19677.892466	6.757541	NaN	452.836235	16.899038	47.081971	2.857472
32	10.433291	117.791230	22326.892046	8.161505	307.707509	412.986834	12.890709	65.733478	5.057311
33	7.414148	235.044534	32555.852537	6.845952	387.175316	411.983364	10.244815	44.489297	3.160624
34	NaN	232.280452	14787.206265	5.474915	NaN	383.981723	12.166937	86.080727	5.029167
35	5.115817	191.952743	19620.545329	6.060713	323.836384	441.748379	10.966486	49.238231	3.902089
36	3.641630	183.908722	24752.072460	5.538314	286.059556	456.860096	9.034067	73.594657	3.464353
37	5.618064	304.235912	17281.975168	6.101084	NaN	399.471566	12.265002	81.588992	2.896547
38	NaN	143.453731	19942.273218	5.890755	NaN	427.130671	22.469892	53.124094	2.907564
39	9.267188	198.614395	24683.723566	6.110612	328.077533	396.876949	16.471969	30.383315	4.324005
40	NaN	233.858996	11703.923907	4.599388	309.039320	349.399633	18.338893	42.677465	3.510004
41	5.331940	194.874065	16658.876503	7.993830	316.675162	335.120398	10.180514	59.572714	4.434820
42	7.145772	238.689929	28780.340432	6.814029	385.975650	332.032706	11.093163	66.138045	5.182591
43	9.920691	202.817483	9973.934059	6.882248	337.350529	333.192470	23.917601	71.833624	4.690707
44	4.758439	183.349454	21568.428779	4.731349	NaN	403.944168	18.668229	66.912400	4.542801
45	5.702926	216.850474	35606.440177	7.184351	NaN	504.638260	16.140790	77.536184	4.137739
46	6.953864	209.638293	10575.186281	4.462707	315.606594	391.184315	13.285334	87.390889	3.195710
47	10.682966	173.375498	15758.740621	5.570784	307.352586	323.807913	10.090870	78.472784	3.999775
48	NaN	129.890572	34415.853146	6.321929	304.535224	470.329169	18.599410	72.403634	4.405586
49	8.757257	200.191400	21536.224687	4.915101	317.882900	404.717799	13.768323	47.930872	3.626135

	ph	Hardness	Solids	Chloramines	Sulfate	Conductivity	Organic_carbon	Trihalomethanes	Turbidity	Potability
250	9.445130	145.805402	13168.529156	9.444471	310.583374	592.659021	8.606397	77.577460	3.875165	1
251	9.024845	128.096691	19859.676476	8.016423	300.150377	451.143481	14.770863	73.778026	3.985251	1
252	NaN	169.974849	23403.637304	8.519730	NaN	475.573562	12.924107	50.861913	2.747313	1
253	6.800119	242.008082	39143.403329	9.501695	187.170714	376.456593	11.432466	73.777275	3.854940	1
254	7.174135	203.408935	20401.102461	7.681806	287.085679	315.549900	14.533510	74.405616	3.939896	1
...	...	...	...	...	...	...	...	...	...	...
3271	4.668102	193.681735	47580.991603	7.166639	359.948574	526.424171	13.894419	66.687695	4.435821	1
3272	7.808856	193.553212	17329.802160	8.061362	NaN	392.449580	19.903225	NaN	2.798243	1
3273	9.419510	175.762646	33155.578218	7.350233	NaN	432.044783	11.039070	69.845400	3.298875	1
3274	5.126763	230.603758	11983.869376	6.303357	NaN	402.883113	11.168946	77.488213	4.708658	1
3275	7.874671	195.102299	17404.177061	7.509306	NaN	327.459760	16.140368	78.698446	2.309149	1

	ph	Hardness	Solids	Chloramines	Sulfate	Conductivity	Organic_carbon	Trihalomethanes	Turbidity	Potability
count	2785.000000	3276.000000	3276.000000	3276.000000	2495.000000	3276.000000	3276.000000	3114.000000	3276.000000	3276.000000
mean	7.080795	196.369496	22014.092526	7.122277	333.775777	426.205111	14.284970	66.396293	3.966786	0.390110
std	1.594320	32.879761	8768.570828	1.583085	41.416840	80.824064	3.308162	16.175008	0.780382	0.487849
min	0.000000	47.432000	320.942611	0.352000	129.000000	181.483754	2.200000	0.738000	1.450000	0.000000
25%	6.093092	176.850538	15666.690297	6.127421	307.699498	365.734414	12.065801	55.844536	3.439711	0.000000
50%	7.036752	196.967627	20927.833607	7.130299	333.073546	421.884968	14.218338	66.622485	3.955028	0.000000
75%	8.062066	216.667456	27332.762127	8.114887	359.950170	481.792304	16.557652	77.337473	4.500320	1.000000
max	14.000000	323.124000	61227.196008	13.127000	481.030642	753.342620	28.300000	124.000000	6.739000	1.000000

	ph	Hardness	Solids	Chloramines	Sulfate	Conductivity	Organic_carbon	Trihalomethanes	Turbidity	Potability
250	9.445130	145.805402	13168.529156	9.444471	310.583374	592.659021	8.606397	77.577460	3.875165	1
251	9.024845	128.096691	19859.676476	8.016423	300.150377	451.143481	14.770863	73.778026	3.985251	1
252	7.036752	169.974849	23403.637304	8.519730	333.073546	475.573562	12.924107	50.861913	2.747313	1
253	6.800119	242.008082	39143.403329	9.501695	187.170714	376.456593	11.432466	73.777275	3.854940	1
254	7.174135	203.408935	20401.102461	7.681806	287.085679	315.549900	14.533510	74.405616	3.939896	1
...	...	...	...	...	...	...	...	...	...	...
3271	4.668102	193.681735	47580.991603	7.166639	359.948574	526.424171	13.894419	66.687695	4.435821	1
3272	7.808856	193.553212	17329.802160	8.061362	333.073546	392.449580	19.903225	66.396293	2.798243	1
3273	9.419510	175.762646	33155.578218	7.350233	333.073546	432.044783	11.039070	69.845400	3.298875	1
3274	5.126763	230.603758	11983.869376	6.303357	333.073546	402.883113	11.168946	77.488213	4.708658	1
3275	7.874671	195.102299	17404.177061	7.509306	333.073546	327.459760	16.140368	78.698446	2.309149	1

	ph	Hardness	Solids	Chloramines	Sulfate	Conductivity	Organic_carbon	Trihalomethanes	Turbidity	Potability
count	3276.000000	3276.000000	3276.000000	3276.000000	3276.000000	3276.000000	3276.000000	3276.000000	3276.000000	3276.000000
mean	7.076341	196.369496	22014.092526	7.122277	333.608364	426.205111	14.284970	66.396293	3.966786	0.390110
std	1.464832	32.879761	8768.570828	1.583085	36.143851	80.824064	3.308162	15.769881	0.780382	0.487849
min	0.227499	47.432000	320.942611	0.352000	129.000000	181.483754	2.200000	0.738000	1.450000	0.000000
25%	6.279317	176.850538	15666.690297	6.127421	317.094638	365.734414	12.065801	56.647656	3.439711	0.000000
50%	7.036752	196.967627	20927.833607	7.130299	333.073546	421.884968	14.218338	66.396293	3.955028	0.000000
75%	7.870050	216.667456	27332.762127	8.114887	350.385756	481.792304	16.557652	76.666609	4.500320	1.000000
max	14.000000	323.124000	61227.196008	13.127000	481.030642	753.342620	28.300000	124.000000	6.739000	1.000000

Data Cleaning¶

Data Visualization¶

What proportion of the dataset represents potable (safe) water samples?¶

How many samples fall into each potability level category?¶

Which chemical is most responsible for very poor water quality?¶

Make a ML model to predict the water quality and score by just giving the custom values¶